OpenMeter MCP for AI. Automate billing and usage tracking for your AI platform.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
OpenMeter connects your AI agent directly to a high-performance billing system. It lets you track usage events, manage customer access limits, and automate subscription billing for any cloud service or API.
You can handle everything from initial user sign-up (`create_customer`) to recording token counts (`ingest_event`), all without manual dashboard intervention.
What AI agents can do with OpenMeter (Usage Metering for AI/Cloud Billing) Automation
Create customer
Creates a new billable customer record within the metering system.
Create entitlement
Sets up specific usage limits or access rights for an existing customer regarding a feature.
Create feature
Defines and registers a new, measurable resource that can be tracked in the billing system.
Record raw usage data (e.g., token count, API calls) using ingest_event so your billing records stay accurate.
Create new billable customer accounts via create_customer or check existing user details with get_customer.
Set specific usage quotas or access rights for a feature using create_entitlement or define the resource itself with create_feature.
Link customers to payment plans by calling create_subscription, which manages their billing cycle.
Start the checkout process for a customer using create_stripe_checkout to collect payments immediately.
Ask an AI about this
Waiting for input…
What AI agents can do with OpenMeter (Usage Metering) MCP Server: 9 Tools for Billing Logic
These nine tools allow your AI agent to manage customer accounts, track usage events, and orchestrate billing workflows in a single system.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using OpenMeter (Usage Metering for AI/Cloud Billing) on VinkiusCreate Customer
Creates a new billable customer record within the metering system.
Create Entitlement
Sets up specific usage limits or access rights for an existing customer regarding a...
Create Feature
Defines and registers a new, measurable resource that can be tracked in the billing...
Create Stripe Checkout
Initiates a payment session on Stripe for collecting funds or starting a paid...
Create Subscription
Links an existing customer to a specific, recurring billing plan.
Delete Subject
Removes a subject (a tracked entity) by its unique internal key for cleanup or data correction.
Get Customer
Retrieves full billing and usage details for a customer using their ID or external key.
Ingest Event
Records a specific usage event (e.g., 150 tokens used) into the metering pipeline...
Upsert Subjects
Updates or adds multiple subject records simultaneously in OpenMeter's data store.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The OpenMeter integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with OpenMeter (Usage Metering for AI/Cloud Billing), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by OpenMeter. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 9 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Billing shouldn't live in a spreadsheet., Solved with Vinkius AI Gateway
Right now, managing usage often means jumping between the raw API logs, the customer dashboard view, and then opening a billing spreadsheet to manually verify if the costs add up. This process is slow. You spend hours trying to reconcile whether 500 tokens logged yesterday actually correspond to the entitlement limit you set last week.
With this MCP server, your agent handles it all. It ingests the usage data via `ingest_event` and instantly updates the customer's true consumption count. The result? Your AI client always has real-time access to accurate billing status without ever needing to open a spreadsheet.
OpenMeter (Usage Metering for AI/Cloud Billing) MCP Server: Manage usage and entitlements.
Manual steps that disappear include logging into the admin panel, searching by customer key, finding the 'Usage' tab, manually counting API calls, and then cross-referencing that count against a separate billing plan document. It’s tedious, error-prone work.
Now, your agent runs `get_customer` or `create_entitlement`. The entire process—check status, update usage, enforce limits—runs in the background via direct API calls. You get reliable, auditable financial data right where you're building your application.
What your AI can actually do with this
You use OpenMeter to run usage-based billing logic right through your AI client. It handles the whole customer life cycle—from defining what gets charged to taking the cash. You don't need some clunky dashboard; you just call the tool.
Defining Your System and Resources
When you start, you gotta define what counts as usage. Use create_feature to register a new resource that needs tracking in your billing system. Then, if you’re dealing with multiple entities tied to that feature, use upsert_subjects or delete_subject. The upsert_subjects tool lets you update or add whole batches of subject records at once.
If you gotta fix data or clean up an old entry, call delete_subject by its unique internal key.
Managing Customers and Usage Tracking
To get started with a new user, you hit the gas on billing setup by calling create_customer, which creates that billable record in your metering system. Need to check what a customer's current status is? Just call get_customer using their ID or external key; it pulls all their usage and billing details right up.
The core of tracking is the ingest_event tool: you send raw data—like 150 tokens used or how many API calls were made—and that tool immediately records that specific usage event, keeping your consumption totals accurate. To set hard limits for a customer on a feature, use create_entitlement. This sets up the specific quota or access rights they're allowed.
Billing and Payment Orchestration
When it comes to money, OpenMeter handles all the complexity. You link customers to recurring charges by calling create_subscription, which manages their entire billing cycle. If you need them to pay now for a one-time service or renew immediately, use create_stripe_checkout to start that payment session on Stripe.
These tools manage collecting funds and starting paid subscriptions right from your agent’s workflow. You can also define the specific access rules by calling create_feature first, then linking those rights to an existing customer via create_entitlement. If you need a brand new billing structure or service that wasn't planned for, run through create_feature to register it.
The Workflow in Action
Your agent acts like your dedicated billing specialist. You let the client call get_customer to verify data. Then, when usage happens, you fire off an ingest_event. The system uses that event count and compares it against the limits set up by a prior call to create_entitlement. If everything looks good, you can then initiate the whole payment process with create_stripe_checkout, or if they're on a recurring plan, you trigger create_subscription.
019e5d40-6067-734a-aa34-038a11ea8805 
Here's how it actually works
The bottom line is: Your AI client handles billing operations by making specific API calls when needed, keeping your entire system auditable.
First, subscribe to the OpenMeter server and provide your API Key.
Next, when a user performs an action (like making an API call), tell your AI client to run ingest_event with the usage data.
Finally, if the usage hits a limit, prompt the agent to use get_customer or create_entitlement to check status and manage access.
Who is this actually for?
This server is for SaaS Founders and FinOps Teams running usage-based products. You're the person who wakes up at 2 AM because a customer hit their token limit and you can't tell if they need another month or just five more credits. This tool lets your agent manage those complex rules instantly.
You use this to automate the billing transition from tracking usage events (ingest_event) to generating invoices, letting your AI client handle customer setup and payment initiation.
You query customer consumption or check entitlement status using natural language prompts against the get_customer tool without needing to build a custom reporting dashboard.
You define and meter new features in code by calling create_feature before rolling them out, ensuring usage is tracked from day one.
What Changes When You Connect
Stop relying on manual dashboard checks. By calling ingest_event, you instantly update the customer's consumption record, ensuring that usage-based limits are enforced in real time.
Onboard new users faster than ever. Use create_customer and then immediately call create_entitlement to define their access rights, all through a single agent conversation.
Collect payments seamlessly. The create_stripe_checkout tool handles the payment initiation flow, allowing your AI client to guide the user right from the usage warning screen.
Manage feature definitions in code. Product Engineers use create_feature to register new resources—like 'Image Generation'—and immediately follow up with create_entitlement to meter it.
Query billing data naturally. You can ask your agent for a customer's status (using get_customer) and get the usage details back, instead of building complex SQL queries.
See it in action
A user hits their token limit.
The system detects high usage. Instead of showing a generic error, the agent runs get_customer to check the remaining balance and then calls create_entitlement to inform the user they need to upgrade, prompting them for payment via create_stripe_checkout.
Onboarding a new enterprise client.
The sales team signs Acme Corp. The agent first runs create_customer, then defines their specific usage rules with create_entitlement, and finally executes create_subscription to start the billing cycle.
Tracking API call volume.
Every time the service makes an external API call, it runs ingest_event with the source and count. This logs the event data—for example, 50 calls from 'GPT-wrapper'—keeping a perfect audit trail.
Removing old or incorrect usage records.
A billing correction is needed for an old client. The agent uses delete_subject to remove the erroneous data, ensuring future reports are accurate and compliant.
The honest tradeoffs
Treating usage as a single number.
Just storing 'Total Tokens Used: 500' in one database field. This fails when you need to know that 300 were for tokens and 200 were for image API calls.
Use ingest_event every time a usage type changes. The event payload must contain the specific metric (e.g., 'tokens') and the count, keeping your data granular.
Managing billing outside of Stripe.
Handling payments manually via webhooks or internal systems that don't integrate with industry standards.
Always use create_stripe_checkout. This tool manages the payment lifecycle and links it correctly to a new create_subscription.
Forgetting to define resources first.
Trying to set an entitlement for 'Video Generation' without first letting the system know that 'Video Generation' is even a feature.
Always start by calling create_feature to register the resource, then use create_entitlement to define usage limits on that new feature.
When It Fits, When It Doesn't
Use this server if your product charges based on consumption or requires strict access control (e.g., tokens, API calls). It's built for billing integrity and customer lifecycle management. Don't use it if you only need simple rate limiting (i.e., 'this user can call the endpoint 10 times per minute'). For basic throttling, a simpler gateway tool is fine. But if you need to track usage for invoicing—that means managing entitlements and subscriptions—then this server is required because of tools like create_entitlement and ingest_event. If your product has zero concept of money or user accounts, ignore it.
Questions you might have
How does OpenMeter use `ingest_event`? +
ingest_event records a usage event (like token counts) directly into the metering pipeline. You pass it the subject key, the metric type, and the count used.
Can I create a new feature using `create_feature`? +
Yes. Calling create_feature registers a new resource (e.g., 'Video Generation') in your system's billing catalog so you can start tracking usage for it.
Do I need to call `get_customer` before creating a subscription? +
It’s best practice. Use get_customer first to verify the customer exists and get their current ID or key, ensuring your create_subscription call targets the correct record.
What is the difference between `create_entitlement` and `create_feature`? +
create_feature registers the resource (the 'what'). create_entitlement defines how much of that resource a customer can actually use (the 'how much').
How do I start billing for a user using OpenMeter? +
You first run create_customer. Then, you define their access with create_entitlement, and finally, initiate payment flow by calling create_stripe_checkout.
What is `upsert_subjects` and how does it handle multiple customer accounts? +
It creates or updates several subject profiles in a single API call. You provide an array of subject objects, letting your agent set up many customers efficiently without calling create_customer repeatedly.
How do I use `create_stripe_checkout` to handle customer payments? +
This tool generates a secure Stripe checkout session URL. Your AI client uses this link, allowing the user to pay immediately and start a new subscription without needing manual dashboard intervention.
When should I use `delete_subject` instead of just updating data? +
Use this tool when you need to fully decommission a customer profile. It removes the subject entirely by key, which is necessary for maintaining accurate billing records and cleaning up old data.
How do I record that a user just consumed 500 tokens in an AI prompt? +
Use the ingest_event tool. Provide the event type (e.g., 'prompt'), the subject (customer ID), and a JSON payload containing the count (e.g., {"tokens": 500}). OpenMeter will handle the aggregation automatically.
Can I check the current status and metadata of a specific billable customer? +
Yes! Use the get_customer tool with the customer's ID or Key. It will return the customer's name, usage attribution settings, and internal identifiers.
How do I set a usage limit or entitlement for a customer? +
Use the create_entitlement tool. You'll need the customerId and a JSON configuration defining the feature and the limit (e.g., a hard limit of 1000 units per month).
We've already built the connector for OpenMeter. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 9 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.